CN113759331B - Radar positioning method, device, equipment and storage medium - Google Patents
Radar positioning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113759331B CN113759331B CN202110182381.XA CN202110182381A CN113759331B CN 113759331 B CN113759331 B CN 113759331B CN 202110182381 A CN202110182381 A CN 202110182381A CN 113759331 B CN113759331 B CN 113759331B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- pose
- radar
- current
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000033001 locomotion Effects 0.000 claims abstract description 126
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000001914 filtration Methods 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000004807 localization Effects 0.000 claims description 2
- 238000013136 deep learning model Methods 0.000 abstract description 2
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000005477 standard model Effects 0.000 description 2
- 101100134058 Caenorhabditis elegans nth-1 gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The embodiment of the invention discloses a radar positioning method, a radar positioning device, radar positioning equipment and a storage medium. The method comprises the following steps: when current frame radar data is received, a first model obstacle pose corresponding to an obstacle in the previous frame radar data and an obstacle movement speed corresponding to the obstacle are obtained; determining a current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the first model obstacle pose and the obstacle movement speed; and performing noise filtering and positioning processing on the radar data of the current frame based on the current estimated obstacle pose, and determining the current radar pose of the target corresponding to the radar data of the current frame. The embodiment of the invention solves the problem of poor real-time performance of radar positioning caused by long time consumption of the deep learning model, realizes parallel processing of obstacle recognition and radar positioning by the recognition model, and improves the real-time performance of radar positioning under the condition of ensuring the accuracy of radar positioning.
Description
Technical Field
The embodiment of the invention relates to the technical field of radar positioning, in particular to a radar positioning method, a radar positioning device, radar positioning equipment and a storage medium.
Background
In the technical field of radar positioning, radar point cloud data acquired based on radar is generally required to be subjected to positioning matching with a high-precision point cloud map, so as to obtain gesture information corresponding to radar positioning. If an obstacle appears in the field of view of the radar, the accuracy of matching the acquired radar point cloud data with the point cloud map is reduced.
The current common noise filtering method is to adopt a deep learning identification model to identify obstacle point clouds in Lei Dadian cloud data, filter the identified obstacle point clouds in radar point cloud data, and then perform positioning matching with a point cloud map.
In the process of realizing the invention, the prior art is found to have at least the following technical problems:
the time consumption of the deep learning recognition model for recognizing the obstacle point cloud is long, and if the model is waited for recognizing the obstacle point cloud and then positioning and matching are carried out, the real-time requirement of a user on radar positioning can be influenced.
Disclosure of Invention
The embodiment of the invention provides a radar positioning method, a radar positioning device, radar positioning equipment and a storage medium, so that the real-time performance of radar positioning is improved under the condition that the radar positioning accuracy is ensured.
In a first aspect, an embodiment of the present invention provides a radar positioning method, including:
When current frame radar data is received, a first model obstacle pose corresponding to an obstacle in the previous frame radar data and an obstacle movement speed corresponding to the obstacle are obtained; the obstacle pose of the first model is obtained by identifying the radar data of the previous frame based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
determining a current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the first model obstacle pose and the obstacle movement speed;
and performing noise filtering and positioning processing on the radar data of the current frame based on the current estimated obstacle pose, and determining the current radar pose of the target corresponding to the radar data of the current frame.
In a second aspect, an embodiment of the present invention further provides a radar positioning device, including:
the obstacle movement speed determining module is used for acquiring a first model obstacle pose corresponding to an obstacle in the previous frame of radar data and the obstacle movement speed corresponding to the obstacle when the current frame of radar data is received; the obstacle pose of the first model is obtained by identifying the radar data of the previous frame based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
The current estimated obstacle pose determining module is used for determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the first model obstacle pose and the obstacle movement speed;
and the target current radar pose determining module is used for carrying out noise filtering and positioning processing on the current frame radar data based on the current estimated obstacle pose and determining the target current radar pose corresponding to the current frame radar data.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the radar positioning methods described above.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer executable instructions which, when executed by a computer processor, are used to perform any of the radar positioning methods referred to above.
The embodiments of the above invention have the following advantages or benefits:
According to the embodiment of the invention, the obstacle pose of the first model obtained by identifying the previous frame of radar data according to the preset identification model and the obstacle movement speed determined based on the obstacle pose of the first model are used for determining the current estimated obstacle pose corresponding to the obstacle in the current frame of radar data, noise filtering and positioning processing are carried out on the current frame of radar data based on the current estimated obstacle pose, and the current radar pose of the target corresponding to the current frame of radar data is determined, so that the parallel processing of obstacle identification and radar positioning by the preset identification model is realized, the problem that the radar positioning instantaneity is poor due to long time consumption of the identification model is solved, and the real-time performance of radar positioning is improved under the condition of ensuring the radar positioning accuracy.
Drawings
Fig. 1 is a flowchart of a radar positioning method according to an embodiment of the present invention.
Fig. 2 is a flowchart of a radar positioning method according to a second embodiment of the present invention.
Fig. 3 is a flowchart of a specific example of a radar positioning method according to the second embodiment of the present invention.
Fig. 4 is a schematic diagram of a radar positioning device according to a third embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a radar positioning method according to an embodiment of the present invention, where the embodiment is applicable to a case of positioning using a radar, and particularly to a case of an obstacle in a positioning scene, the method may be performed by a radar positioning device, the device may be implemented in software and/or hardware, and the device may be configured in a radar apparatus or a terminal apparatus. The method specifically comprises the following steps:
s110, when the radar data of the current frame are received, the first model obstacle pose corresponding to the obstacle in the radar data of the previous frame and the obstacle movement speed corresponding to the obstacle are obtained.
Specifically, the radar device acquires at least one frame of radar data at a preset acquisition frequency. For example, the current frame of radar data may be an nth frame of radar data, the last frame of radar data being an N-1 frame of radar data, where N is a natural number greater than 1.
In this embodiment, the first model obstacle pose is obtained by identifying the previous frame of radar data based on a preset identification model, and the obstacle movement speed includes a movement speed determined based on the first model obstacle pose.
Exemplary model types of the preset recognition model include, but are not limited to, convolutional neural network models, error back propagation neural network models, deep learning models, and the like.
In one embodiment, optionally, acquiring the first model obstacle pose corresponding to the obstacle and the obstacle movement speed corresponding to the obstacle in the previous frame of radar data includes: when the radar data of the previous frame are received, identifying the radar data of the previous frame based on a preset identification model, and determining the first model obstacle pose corresponding to at least one obstacle in the radar data of the previous frame; if the previous frame of radar data is the first frame of radar data, setting the obstacle movement speed corresponding to each obstacle as a preset movement speed; if the previous frame of radar data is the N-1 frame of radar data, determining the movement speed of the obstacle corresponding to at least one obstacle in the previous frame of radar data according to the pose of the obstacle of the first model and the pose of the obstacle of the second model corresponding to at least one obstacle in the N-2 frame of radar data respectively; wherein N is a natural number greater than 2.
The first model obstacle pose is used for representing angle information and position information of a bounding box corresponding to an obstacle in the previous frame of radar data.
In one embodiment, optionally, training radar data is input into an initial preset recognition model, model parameters of the initial preset recognition model are adjusted based on standard model obstacle pose and output predicted model obstacle pose, and when preset ending conditions are met, a trained preset recognition model is obtained. The predetermined end condition may be, for example, that a loss function determined based on the standard model obstacle pose and the output predicted model obstacle pose converges or is smaller than a predetermined loss threshold.
In one embodiment, the radar device is in a stationary state when the first frame of radar data is received, no real-time positioning is required, or the radar device begins to move after the first frame of radar data is processed. Wherein, the preset movement speed may be 0, as an example. In another embodiment, the previous frame of radar data is the N-1 st frame of radar data, N is a natural number greater than 2, specifically, when the N-2 nd frame of radar data is received, the N-2 nd frame of radar data is identified based on a preset identification model, the second model obstacle pose corresponding to at least one obstacle in the N-2 nd frame of radar data is determined, and the obstacle movement speed corresponding to at least one obstacle in the N-1 st frame of radar data is determined based on the first model obstacle pose corresponding to at least one obstacle in the N-1 st frame of radar data and the second model obstacle pose corresponding to at least one obstacle in the N-2 nd frame of radar data.
S120, determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the obstacle pose and the obstacle movement speed of the first model.
In one embodiment, optionally, determining a current estimated obstacle pose corresponding to an obstacle in the radar data of the current frame based on the first model obstacle pose and the obstacle movement speed includes: acquiring the previous radar pose corresponding to the equipment motion data and the previous frame of radar data; the device motion data are motion data of radar devices in inter-frame interval time corresponding to the radar data of the previous frame and the radar data of the current frame; determining a predicted current radar pose based on the equipment motion data and the previous radar pose; and determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the estimated current radar pose, the previous radar pose, the first model obstacle pose and the obstacle movement speed.
Wherein the device motion data comprises, in particular, a motion speed and an angular speed of the radar device within an inter-frame time interval. Illustratively, in the field of unmanned vehicle technology, a device movement velocity recorded in a chassis or IMU (Inertial Measurement Unit ) on the unmanned vehicle where the radar device is located is obtained.
In one embodiment, optionally, the estimated current radar pose satisfies the formula:
wherein,representing a rotation matrix in the estimated current radar pose, < +.>Representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing spatial position coordinates in the previous radar pose, ω represents angular velocity in the device motion data, v represents motion velocity in the device motion data, and Δt represents inter-frame interval time of the previous frame radar data corresponding to the current frame radar data.
In one embodiment, optionally, determining the current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the estimated current radar pose, the previous radar pose, the first model obstacle pose, and the obstacle movement speed includes: determining a current initial obstacle pose corresponding to an obstacle in the radar data of the current frame based on the estimated current radar pose, the previous radar pose and the first model obstacle pose; and determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the obstacle movement speed and the current initial obstacle pose.
In one embodiment, optionally, the current estimated obstacle pose satisfies the formula:
Wherein,representing a rotation matrix in the current estimated obstacle pose, +.>Representing a currently estimated obstacle
The spatial position coordinates in the object pose,representing a rotation matrix in the current initial obstacle pose, < > in->Representing spatial position coordinates in the current initial obstacle pose,/->Represents the obstacle movement speed, delta T represents the inter-frame interval time between the N-2 th frame radar data and the last frame radar data, and the delta T represents the difference between the N-2 th frame radar data and the last frame radar data>Representing a rotation matrix in the estimated current radar pose,representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing the spatial position coordinates in the last radar pose, R box Representing a rotation matrix in the pose of the obstacle of the first model, t box Representing spatial position coordinates in the first model obstacle pose.
S130, performing noise filtering and positioning processing on the radar data of the current frame based on the current estimated obstacle pose, and determining the current radar pose of the target corresponding to the radar data of the current frame.
On the basis of the above embodiment, optionally, based on the current estimated obstacle pose, noise filtering and positioning processing are performed on the radar data of the current frame, and determining the current radar pose of the target corresponding to the radar data of the current frame includes: based on the current estimated pose of the obstacle and the size of the obstacle corresponding to the obstacle, carrying out noise filtering processing on the radar data of the current frame; the obstacle size is obtained by identifying radar data containing the obstacle based on a preset identification model; and determining the current radar pose of the target corresponding to the radar data of the current frame based on the radar data of the current frame after the noise filtering processing and the point cloud map data.
The obstacle size may be obtained by identifying the previous frame of radar data by using a preset identification model, and the obstacle size may be a size of a bounding box corresponding to the obstacle. If the radar data of the previous frame also contains the obstacle, the obstacle size can also be obtained by identifying the radar data of the previous frame by a preset identification model. The radar data specifically corresponding to the obstacle size is not limited here.
Specifically, based on the current estimated pose of the obstacle and the size of the obstacle corresponding to the obstacle, deleting the obstacle radar data in the radar data of the current frame to obtain the radar data of the current frame after noise filtering processing. Specifically, an ICP (Iterative Closeat Point) algorithm or an NDT (Normal Distributions Transform, normal distribution transformation) improved algorithm is adopted to match and locate the current frame radar data after noise filtering processing with the point cloud map data, so as to obtain a target current radar pose (R) corresponding to the current frame radar data n ,t n )。
According to the technical scheme, the obstacle pose of the first model obtained by identifying the previous frame of radar data according to the preset identification model and the obstacle movement speed determined based on the obstacle pose of the first model are used for determining the current estimated obstacle pose corresponding to the obstacle in the current frame of radar data, noise filtering and positioning processing are carried out on the current frame of radar data based on the current estimated obstacle pose, the current radar pose of the target corresponding to the current frame of radar data is determined, obstacle identification and radar positioning parallel processing of the preset identification model are achieved, the problem that radar positioning instantaneity is poor due to long time consumption of the identification model is solved, and the instantaneity of radar positioning is improved under the condition that radar positioning accuracy is guaranteed.
Example two
Fig. 2 is a flowchart of a radar positioning method according to a second embodiment of the present invention, and the technical solution of this embodiment is further refinement based on the foregoing embodiment. Optionally, the determining, according to the pose of the first model obstacle and the pose of the second model obstacle corresponding to at least one obstacle in the N-2 th frame of radar data, the moving speed of the obstacle corresponding to at least one obstacle in the last frame of radar data includes: matching the first model obstacle pose with the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data according to the first model obstacle pose corresponding to each obstacle; if a second model obstacle pose which is successfully matched with the first model obstacle pose exists, determining an obstacle movement speed corresponding to the obstacle based on the first model obstacle pose and the second model obstacle pose which is successfully matched; and if the second model obstacle pose successfully matched with the first model obstacle pose does not exist, setting the obstacle movement speed corresponding to the obstacle as a preset movement speed.
The specific implementation steps of the embodiment include:
and S210, when the radar data of the current frame are received, acquiring a first model obstacle pose corresponding to the obstacle in the radar data of the previous frame.
In this embodiment, the previous frame of radar data is the N-1 st frame of radar data and N is a natural number greater than 2.
Specifically, when the previous frame of radar data is received, the previous frame of radar data is identified based on a preset identification model, and the first model obstacle pose corresponding to at least one obstacle in the previous frame of radar data is determined.
S220, matching the first model obstacle pose with the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data according to the first model obstacle pose corresponding to each obstacle.
Specifically, when N-2 frames of radar data are received, the N-2 frames of radar data are identified based on a preset identification model, and the second model obstacle pose corresponding to at least one obstacle in the N-2 frames of radar data is determined. Specifically, the obstacle pose list corresponding to the radar data of the previous frame includes at least one first model obstacle pose corresponding to an obstacle, and the obstacle pose list corresponding to the radar data of the N-2 frame includes at least one second model obstacle pose corresponding to an obstacle.
S230, judging whether a second model obstacle pose successfully matched with the first model obstacle pose exists, if so, executing S250, and if not, executing S240.
In one embodiment, optionally, matching the first model obstacle pose with a second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data, respectively, includes: and respectively determining the obstacle distance between the obstacle and at least one obstacle in the N-2 frame radar data based on the second model obstacle pose corresponding to the at least one obstacle in the first model obstacle pose and the N-2 frame radar data, and taking the second model obstacle pose corresponding to the obstacle distance smaller than the preset distance threshold as the second model obstacle pose successfully matched with the first model obstacle pose.
Wherein, illustratively, based on the nearest neighbor selection association algorithm, it is determined whether there is a second model obstacle pose that successfully matches the first model obstacle pose.
Specifically, a first obstacle and a second obstacle corresponding to a first model obstacle pose and a second model obstacle pose, where the obstacle distance is smaller than a preset distance threshold, are used as the same obstacle. And if the obstacle pose corresponding to the first model obstacle pose is not existed and is smaller than the second model obstacle pose corresponding to the preset distance threshold, indicating that the N-2 th frame radar data does not exist the obstacle data corresponding to the obstacle, and the obstacle belongs to a new obstacle.
For example, the obstacle pose list corresponding to the previous frame of radar data includes first model obstacle poses corresponding to the obstacle A1, the obstacle B1 and the obstacle C1, and the obstacle pose list corresponding to the N-2 frame of radar data includes second model obstacle poses corresponding to the obstacle A2, the obstacle C2 and the obstacle D2, and if the obstacle distance determined based on the first model obstacle poses corresponding to the obstacle A1 and the obstacle A2 and the second model obstacle poses corresponding to the obstacle A2 is smaller than the preset distance threshold, the obstacle A1 and the obstacle A2 are the same obstacle. And if the obstacle distances determined based on the first model obstacle pose corresponding to the obstacle B1 and the second model obstacle pose corresponding to the obstacle A2, the obstacle C2 and the obstacle D2 respectively are all greater than or equal to a preset distance threshold, indicating that the obstacle B1 is a new obstacle.
S240, setting the movement speed of the obstacle corresponding to the obstacle as a preset movement speed, and executing S260.
Wherein, the preset motion speed is 0, for example.
S250, determining the obstacle movement speed corresponding to the obstacle based on the first model obstacle pose and the second model obstacle pose successfully matched.
Wherein, concretely, the obstacle movement speed satisfies the formula:
wherein V is box Representing the speed of movement of an obstacle, t n-1 Representing the spatial position coordinates, t, in the pose of the obstacle of the first model n-2 Representing the spatial position coordinates in the pose of the obstacle of the second model, wherein DeltaT represents the N-2 frame radar data and the last frame radar data pairThe inter-frame space time is to be taken.
S260, determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the obstacle pose and the obstacle movement speed of the first model.
S270, noise filtering and positioning processing are carried out on the radar data of the current frame based on the current estimated obstacle pose, and the current radar pose of the target corresponding to the radar data of the current frame is determined.
Fig. 3 is a flowchart of a specific example of a radar positioning method according to the second embodiment of the present invention. Specifically, when 1 st frame radar data is received, the 1 st frame radar data is identified based on a preset identification model, a first model obstacle pose and an obstacle size corresponding to the 1 st frame radar data are obtained, noise filtering processing is performed on the 1 st frame radar data based on the model obstacle pose and the obstacle size, pure point cloud is specifically obtained, the 1 st frame radar data after the noise filtering processing is obtained, and the pure point cloud is subjected to positioning matching with a point cloud map, so that a first frame radar pose corresponding to the 1 st frame radar data is obtained. Since the radar device is in a stationary state when the first frame of radar data is received, no requirement is placed on positioning instantaneity, or the radar device starts to move after the first frame of radar data is processed. At this time, the obstacle movement speed corresponding to the 1 st frame radar data is 0.
When 2 nd frame radar data is received, in the process of recognizing the 2 nd frame radar data by a preset recognition model, based on the acquired equipment motion speed and the first frame radar pose, determining the estimated radar pose corresponding to the 2 nd frame radar data, based on the estimated radar pose, the acquired first frame radar pose corresponding to the 1 st frame radar data, the first model obstacle pose and the obstacle motion speed, determining the estimated obstacle pose corresponding to the obstacle in the 2 nd frame radar data, and based on the estimated obstacle pose, performing noise filtering processing on the 2 nd frame radar data to obtain pure point cloud, specifically, performing positioning matching on the pure point cloud and a point cloud map to obtain a second frame radar pose corresponding to the 2 nd frame radar data. And determining the obstacle movement speed corresponding to the 2 nd frame radar data based on the first model obstacle pose and the second model obstacle pose output by the preset recognition model.
When N frames of radar data are received, in the process of identifying the N frames of radar data by a preset identification model, based on the acquired equipment motion speed and the N-1 frames of radar pose, determining the estimated radar pose corresponding to the N frames of radar data, based on the estimated radar pose, the N-1 frames of radar pose corresponding to the acquired N-1 frames of radar data, the first model obstacle pose and the obstacle motion speed, determining the estimated obstacle pose corresponding to the obstacle in the N frames of radar data, and filtering noise of the N frames of radar data based on the estimated obstacle pose to obtain pure point cloud, specifically, positioning and matching the pure point cloud with a point cloud map to obtain the N frames of radar pose corresponding to the N frames of radar data. And determining the obstacle movement speed corresponding to the radar data of the nth frame based on the obstacle pose of the nth-1 model and the obstacle pose of the nth model output by the preset recognition model.
According to the technical scheme, the first model obstacle pose is matched with the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data, the obstacle movement speed corresponding to the obstacle is determined based on the first model obstacle pose and the second model obstacle pose successfully matched, the problem of determining the obstacle movement speed is solved, the obstacle pose corresponding to the current frame radar data is estimated based on the obstacle movement speed, and the real-time performance of radar positioning is improved under the condition that the radar positioning accuracy is ensured.
Example III
Fig. 4 is a schematic diagram of a radar positioning device according to a third embodiment of the present invention. The embodiment can be suitable for the situation of positioning by adopting a radar, particularly suitable for the situation that an obstacle exists in a positioning scene, the device can be realized by adopting a software and/or hardware mode, and the device can be configured in radar equipment or terminal equipment. The radar positioning device includes: an obstacle movement speed determination module 310, a current estimated obstacle pose determination module 320, and a target current radar pose determination module 330.
The obstacle movement speed determining module 310 is configured to obtain, when receiving the current frame of radar data, a first model obstacle pose corresponding to an obstacle in the previous frame of radar data and an obstacle movement speed corresponding to the obstacle; the obstacle pose of the first model is obtained by identifying the previous frame of radar data based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
The current estimated obstacle pose determining module 320 is configured to determine a current estimated obstacle pose corresponding to an obstacle in the radar data of the current frame based on the first model obstacle pose and the obstacle movement speed;
the target current radar pose determining module 330 is configured to perform noise filtering and positioning processing on the current frame radar data based on the current estimated obstacle pose, and determine a target current radar pose corresponding to the current frame radar data.
According to the technical scheme, the obstacle pose of the first model obtained by identifying the previous frame of radar data according to the preset identification model and the obstacle movement speed determined based on the obstacle pose of the first model are used for determining the current estimated obstacle pose corresponding to the obstacle in the current frame of radar data, noise filtering and positioning processing are carried out on the current frame of radar data based on the current estimated obstacle pose, the current radar pose of the target corresponding to the current frame of radar data is determined, obstacle identification and radar positioning parallel processing of the preset identification model are achieved, the problem that radar positioning instantaneity is poor due to long time consumption of the identification model is solved, and the instantaneity of radar positioning is improved under the condition that radar positioning accuracy is guaranteed.
On the basis of the above technical solution, optionally, the obstacle movement speed determining module 310 includes:
the first model obstacle pose determining unit is used for identifying the previous frame of radar data based on a preset identification model when the previous frame of radar data is received, and determining first model obstacle poses corresponding to at least one obstacle in the previous frame of radar data respectively;
an obstacle movement speed determining unit, configured to set an obstacle movement speed corresponding to each obstacle as a preset movement speed if the previous frame of radar data is the first frame of radar data; if the previous frame of radar data is the N-1 frame of radar data, determining the movement speed of the obstacle corresponding to at least one obstacle in the previous frame of radar data according to the pose of the obstacle of the first model and the pose of the obstacle of the second model corresponding to at least one obstacle in the N-2 frame of radar data respectively; wherein N is a natural number greater than 2.
On the basis of the above technical solution, optionally, the obstacle movement speed determining unit includes:
the first model obstacle pose matching subunit is used for matching the first model obstacle pose with the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data respectively according to the first model obstacle pose corresponding to each obstacle respectively;
An obstacle movement speed determining subunit, configured to determine, if there is a second model obstacle pose successfully matched with the first model obstacle pose, an obstacle movement speed corresponding to the obstacle based on the first model obstacle pose and the second model obstacle pose successfully matched; and if the second model obstacle pose successfully matched with the first model obstacle pose does not exist, setting the obstacle movement speed corresponding to the obstacle as a preset movement speed.
On the basis of the above technical solution, optionally, the obstacle movement speed determining subunit is specifically configured to:
and respectively determining the obstacle distance between the obstacle and at least one obstacle in the N-2 frame radar data based on the second model obstacle pose corresponding to the at least one obstacle in the first model obstacle pose and the N-2 frame radar data, and taking the second model obstacle pose corresponding to the obstacle distance smaller than the preset distance threshold as the second model obstacle pose successfully matched with the first model obstacle pose.
Based on the above technical solution, optionally, the current estimated obstacle pose determining module 320 includes:
the device motion data acquisition unit is used for acquiring the previous radar pose corresponding to the device motion data and the previous frame of radar data; the device motion data are motion data of radar devices in inter-frame interval time corresponding to the radar data of the previous frame and the radar data of the current frame;
The estimated current radar pose determining unit is used for determining the estimated current radar pose based on the equipment motion data and the previous radar pose;
the current estimated obstacle pose determining unit is used for determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the estimated current radar pose, the previous radar pose, the obstacle pose of the first model and the obstacle movement speed.
Based on the technical scheme, the estimated current radar pose can optionally meet the formula:
wherein,representing a rotation matrix in the estimated current radar pose, < +.>Representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing spatial position coordinates in the previous radar pose, ω represents angular velocity in the device motion data, v represents motion velocity in the device motion data, and Δt represents inter-frame interval time of the previous frame radar data corresponding to the current frame radar data.
Based on the above technical solution, optionally, the current estimated obstacle pose determining unit is specifically configured to:
determining a current initial obstacle pose corresponding to an obstacle in the radar data of the current frame based on the estimated current radar pose, the previous radar pose and the first model obstacle pose;
And determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the obstacle movement speed and the current initial obstacle pose.
Based on the above technical scheme, optionally, the current estimated pose of the obstacle satisfies the formula:
wherein,representing a rotation matrix in the current estimated obstacle pose, +.>Representing spatial position coordinates in the current estimated obstacle pose, +.>Representing a rotation matrix in the current initial obstacle pose, < > in->Representing spatial position coordinates in the current initial obstacle pose,/->Represents the obstacle movement speed, delta T represents the inter-frame interval time between the N-2 th frame radar data and the last frame radar data, and the delta T represents the difference between the N-2 th frame radar data and the last frame radar data>Representing estimated current lightningReaching the rotation matrix in pose, +.>Representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing the spatial position coordinates in the last radar pose, R box Representing a rotation matrix in the pose of the obstacle of the first model, t box Representing spatial position coordinates in the first model obstacle pose.
Based on the above technical solution, optionally, the target current radar pose determining module 330 is specifically configured to:
Based on the current estimated pose of the obstacle and the size of the obstacle corresponding to the obstacle, carrying out noise filtering processing on the radar data of the current frame; the obstacle size is obtained by identifying radar data containing the obstacle based on a preset identification model;
and determining the current radar pose of the target corresponding to the radar data of the current frame based on the radar data of the current frame after the noise filtering processing and the point cloud map data.
The radar positioning device provided by the embodiment of the invention can be used for executing the radar positioning method provided by the embodiment of the invention, and has the corresponding functions and beneficial effects of the executing method.
It should be noted that, in the embodiment of the radar positioning device, each unit and module included are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Example IV
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention, which provides services for implementing the radar positioning method according to the above embodiment of the present invention, and the radar positioning device according to the above embodiment may be configured. Fig. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the electronic device 12 is in the form of a general purpose computing device. Components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20. As shown in fig. 5, the network adapter 20 communicates with other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the radar localization method provided by the embodiment of the present invention.
Through the electronic equipment, the problem that the real-time performance of radar positioning is poor due to long time consumption of the identification model is solved, and the real-time performance of radar positioning is improved under the condition that the accuracy of radar positioning is ensured.
Example five
A fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a radar positioning method, the method comprising:
when the radar data of the current frame are received, the pose of a first model obstacle corresponding to the obstacle in the radar data of the previous frame and the movement speed of the obstacle corresponding to the obstacle are obtained; the obstacle pose of the first model is obtained by identifying the previous frame of radar data based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
determining a current estimated obstacle pose corresponding to an obstacle in the radar data of the current frame based on the obstacle pose of the first model and the obstacle movement speed;
And performing noise filtering and positioning processing on the radar data of the current frame based on the current estimated obstacle pose, and determining the current radar pose of the target corresponding to the radar data of the current frame.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the above method operations, and may also perform the related operations in the radar positioning method provided in any embodiment of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. A radar positioning method, comprising:
when current frame radar data is received, a first model obstacle pose corresponding to an obstacle in the previous frame radar data and an obstacle movement speed corresponding to the obstacle are obtained; the obstacle pose of the first model is obtained by identifying the radar data of the previous frame based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
Determining a current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the first model obstacle pose and the obstacle movement speed;
based on the current estimated obstacle pose, performing noise filtering and positioning processing on the radar data of the current frame, and determining the current radar pose of a target corresponding to the radar data of the current frame;
the determining, based on the first model obstacle pose and the obstacle movement speed, a current estimated obstacle pose corresponding to the obstacle in the current frame radar data includes:
acquiring equipment motion data and a previous radar pose corresponding to the previous frame of radar data; the device motion data are motion data of radar devices in inter-frame interval time corresponding to the radar data of the previous frame and the radar data of the current frame;
determining an estimated current radar pose based on the equipment motion data and the last radar pose;
determining a current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the estimated current radar pose, the previous radar pose, the first model obstacle pose and the obstacle movement speed;
The step of performing noise filtering and positioning processing on the radar data of the current frame based on the current estimated obstacle pose, and determining the current radar pose of the target corresponding to the radar data of the current frame comprises the following steps:
performing noise filtering processing on the radar data of the current frame based on the current estimated obstacle pose and the obstacle size corresponding to the obstacle; the obstacle size is obtained by identifying radar data containing the obstacle based on a preset identification model;
and determining the current radar pose of a target corresponding to the current frame radar data based on the current frame radar data after noise filtering processing and the point cloud map data.
2. The method according to claim 1, wherein the obtaining the first model obstacle pose corresponding to the obstacle in the previous frame of radar data and the obstacle movement speed corresponding to the obstacle includes:
when the radar data of the previous frame are received, identifying the radar data of the previous frame based on a preset identification model, and determining the first model obstacle pose corresponding to at least one obstacle in the radar data of the previous frame;
if the previous frame of radar data is the first frame of radar data, setting the obstacle movement speed corresponding to each obstacle as a preset movement speed;
If the previous frame of radar data is the N-1 frame of radar data, determining the obstacle movement speed corresponding to at least one obstacle in the previous frame of radar data according to the second model obstacle pose corresponding to at least one obstacle in the first model obstacle pose and the N-2 frame of radar data respectively; wherein N is a natural number greater than 2.
3. The method according to claim 2, wherein determining the obstacle movement speed of at least one obstacle in the previous frame of radar data according to the first model obstacle pose and the second model obstacle pose corresponding to the at least one obstacle in the N-2 frame of radar data, respectively, comprises:
matching the first model obstacle pose with the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data according to the first model obstacle pose corresponding to each obstacle;
if a second model obstacle pose which is successfully matched with the first model obstacle pose exists, determining an obstacle movement speed corresponding to the obstacle based on the first model obstacle pose and the second model obstacle pose which is successfully matched;
And if the second model obstacle pose successfully matched with the first model obstacle pose does not exist, setting the obstacle movement speed corresponding to the obstacle as a preset movement speed.
4. The method of claim 3, wherein the matching the first model obstacle pose with a second model obstacle pose respectively corresponding to at least one obstacle in the N-2 th frame of radar data comprises:
and respectively determining the obstacle distance between the obstacle and at least one obstacle in the N-2 frame radar data based on the first model obstacle pose and the second model obstacle pose corresponding to at least one obstacle in the N-2 frame radar data, and taking the second model obstacle pose corresponding to the obstacle distance smaller than a preset distance threshold as the second model obstacle pose successfully matched with the first model obstacle pose.
5. The method of claim 1, wherein the estimated current radar pose satisfies the formula:
wherein,representing a rotation matrix in the estimated current radar pose, < +.>Representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing spatial position coordinates in the previous radar pose, ω represents angular velocity in the device motion data, v represents motion velocity in the device motion data, and Δt represents inter-frame interval time of the previous frame radar data corresponding to the current frame radar data.
6. The method of claim 1, wherein the determining the current predicted obstacle pose corresponding to the obstacle in the current frame of radar data based on the predicted current radar pose, the previous radar pose, the first model obstacle pose, and the obstacle movement speed comprises:
determining a current initial obstacle pose corresponding to the obstacle in the current frame radar data based on the estimated current radar pose, the previous radar pose and the first model obstacle pose;
and determining the current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the obstacle movement speed and the current initial obstacle pose.
7. The method of claim 6, wherein the current predicted obstacle pose satisfies the formula:
Wherein,representing a rotation matrix in the current estimated obstacle pose, +.>Representing spatial position coordinates in the current estimated obstacle pose, +.>Representing a rotation matrix in the current initial obstacle pose, < > in->Representing spatial position coordinates in the current initial obstacle pose,/->Represents the obstacle movement speed, delta T represents the inter-frame interval time between the N-2 th frame radar data and the last frame radar data, and the delta T represents the difference between the N-2 th frame radar data and the last frame radar data>Representing a rotation matrix in the estimated current radar pose, < +.>Representing the spatial position coordinates in the estimated current radar pose, R n-1 Representing a rotation matrix, t, in the last radar pose n-1 Representing the spatial position coordinates in the last radar pose, R box Representing a rotation matrix in the pose of the obstacle of the first model, t box Representing spatial position coordinates in the first model obstacle pose.
8. A radar positioning device, comprising:
the obstacle movement speed determining module is used for acquiring a first model obstacle pose corresponding to an obstacle in the previous frame of radar data and the obstacle movement speed corresponding to the obstacle when the current frame of radar data is received; the obstacle pose of the first model is obtained by identifying the radar data of the previous frame based on a preset identification model, and the obstacle movement speed comprises a movement speed determined based on the obstacle pose of the first model;
The current estimated obstacle pose determining module is used for determining the current estimated obstacle pose corresponding to the obstacle in the radar data of the current frame based on the first model obstacle pose and the obstacle movement speed;
the target current radar pose determining module is used for carrying out noise filtering and positioning processing on the current frame radar data based on the current estimated obstacle pose and determining the target current radar pose corresponding to the current frame radar data;
the current estimated obstacle pose determining module comprises:
the device motion data acquisition unit is used for acquiring device motion data and a previous radar pose corresponding to the previous frame of radar data; the device motion data are motion data of radar devices in inter-frame interval time corresponding to the radar data of the previous frame and the radar data of the current frame;
the estimated current radar pose determining unit is used for determining an estimated current radar pose based on the equipment motion data and the previous radar pose;
a current estimated obstacle pose determining unit, configured to determine a current estimated obstacle pose corresponding to the obstacle in the current frame radar data based on the estimated current radar pose, the previous radar pose, the first model obstacle pose, and the obstacle movement speed;
The target current radar pose determining module is specifically configured to:
performing noise filtering processing on the radar data of the current frame based on the current estimated obstacle pose and the obstacle size corresponding to the obstacle; the obstacle size is obtained by identifying radar data containing the obstacle based on a preset identification model;
and determining the current radar pose of a target corresponding to the current frame radar data based on the current frame radar data after noise filtering processing and the point cloud map data.
9. An electronic device, the electronic device comprising:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the radar localization method of any one of claims 1-7.
10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the radar positioning method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182381.XA CN113759331B (en) | 2021-02-07 | 2021-02-07 | Radar positioning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182381.XA CN113759331B (en) | 2021-02-07 | 2021-02-07 | Radar positioning method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113759331A CN113759331A (en) | 2021-12-07 |
| CN113759331B true CN113759331B (en) | 2024-04-12 |
Family
ID=78786632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110182381.XA Active CN113759331B (en) | 2021-02-07 | 2021-02-07 | Radar positioning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113759331B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018496A (en) * | 2018-01-10 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Obstacle recognition method and device, electronic equipment, storage medium |
| CN110646787A (en) * | 2018-06-27 | 2020-01-03 | 三星电子株式会社 | Self-motion estimation method and device and model training method and device |
| CN111797650A (en) * | 2019-04-09 | 2020-10-20 | 广州文远知行科技有限公司 | Obstacle identification method and device, computer equipment and storage medium |
| WO2020216316A1 (en) * | 2019-04-26 | 2020-10-29 | 纵目科技（上海）股份有限公司 | Driver assistance system and method based on millimetre wave radar, terminal, and medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109059902B (en) * | 2018-09-07 | 2021-05-28 | 百度在线网络技术（北京）有限公司 | Relative pose determination method, device, equipment and medium |
| CN109300143B (en) * | 2018-09-07 | 2021-07-27 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for determining motion vector field, storage medium and vehicle |
| US11105921B2 (en) * | 2019-02-19 | 2021-08-31 | Honeywell International Inc. | Systems and methods for vehicle navigation |
-
2021
- 2021-02-07 CN CN202110182381.XA patent/CN113759331B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018496A (en) * | 2018-01-10 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Obstacle recognition method and device, electronic equipment, storage medium |
| CN110646787A (en) * | 2018-06-27 | 2020-01-03 | 三星电子株式会社 | Self-motion estimation method and device and model training method and device |
| CN111797650A (en) * | 2019-04-09 | 2020-10-20 | 广州文远知行科技有限公司 | Obstacle identification method and device, computer equipment and storage medium |
| WO2020216316A1 (en) * | 2019-04-26 | 2020-10-29 | 纵目科技（上海）股份有限公司 | Driver assistance system and method based on millimetre wave radar, terminal, and medium |
Non-Patent Citations (2)
| Title |
|---|
| "Deep-Learning Methods for Hand-Gesture Recognition Using Ultra-Wideband Radar";SRUTHY SKARIA et al.;《IEEE ACCESS》;第8卷;第205380-203590页 * |
| "动态环境下无人地面车辆点云地图快速重定位方法";郑壮壮等;《兵工学报》;第41卷(第8期);第1581-1589页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113759331A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6683234B2 (en) | Audio data processing method, device, equipment and program | |
| EP3627180B1 (en) | Sensor calibration method and device, computer device, medium, and vehicle | |
| US11215996B2 (en) | Method and device for controlling vehicle, device, and storage medium | |
| US10983596B2 (en) | Gesture recognition method, device, electronic device, and storage medium | |
| US20190066671A1 (en) | Far-field speech awaking method, device and terminal device | |
| EP3627181A1 (en) | Multi-sensor calibration method, multi-sensor calibration device, computer device, medium and vehicle | |
| JP2020040654A (en) | Yaw-angle determination method, yaw-angle determination device, equipment, computer-readable storage medium | |
| EP3624085A1 (en) | Method for recognizing traffic light, device, storage medium, and vehicle | |
| CN109635861B (en) | Data fusion method and device, electronic equipment and storage medium | |
| CN113971727A (en) | Training method, device, equipment and medium of semantic segmentation model | |
| CN111814746A (en) | Method, device, equipment and storage medium for identifying lane line | |
| CN109635868B (en) | Method and device for determining obstacle type, electronic device and storage medium | |
| CN112650300B (en) | Unmanned aerial vehicle obstacle avoidance method and device | |
| CN112798004B (en) | Positioning method, device and equipment for vehicle and storage medium | |
| CN109284108B (en) | Unmanned vehicle data storage method and device, electronic equipment and storage medium | |
| CN112528859A (en) | Lane line detection method, device, equipment and storage medium | |
| CN110826036A (en) | User operation behavior safety identification method and device and electronic equipment | |
| CN114103944B (en) | Workshop time interval adjusting method, device and equipment | |
| CN110363193B (en) | Vehicle weight recognition method, device, equipment and computer storage medium | |
| WO2020134674A1 (en) | Palmprint identification method, apparatus, computer device, and storage medium | |
| CN111063011A (en) | Face image processing method, device, equipment and medium | |
| CN113759331B (en) | Radar positioning method, device, equipment and storage medium | |
| US20190066662A1 (en) | Priors adaptation for conservative training of acoustic model | |
| CN113721240B (en) | Target association method, device, electronic equipment and storage medium | |
| CN114578402A (en) | Target position information determining method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |